Are compounds and phrases constructed by the same combinatorial principles? This is a long-standing topic in linguistic theory. As a highly isolating language, Chinese offers a particularly revealing case: its word–phrase boundary is weakly marked, thus compound-internal relations often parallel phrase-level syntactic relations. Although this continuity is well described in Chinese linguistics, no operational test has yet examined whether the same principles are similarly represented across the two levels. PLMs provide a shared representational space for operationalizing this question. Motivated by this idea, we build CompPhrase-7, a parallel Chinese compound–phrase dataset covering seven shared relation types, and conduct a multi-dimensional probing study of Chinese-language PLMs, which separates three levels of cross-scale continuity: transferable feature information, aligned category geometry, and localized dimension-level causal support. The results show a clear dissociation: feature transfer is stable across models; category geometry depends strongly on pre-training regime; and localized causal support is not detected. The findings point to a differentiated view of Chinese combinatorial principles: compounds and phrases retain comparable relational cues, while lexicalization reshapes how those cues are organized once phrase-like structures become words. This study connects a long-standing linguistic question to a more precise computational representation, showing that continuity can surface as transferable information without shared geometry or localized causal implementation.